New Cask logo

New Cask

Community
malob
new-cask

This skill should be used when the user asks to "add a cask to homebrew", "create a homebrew cask", "add an app to homebrew", "new cask for", "homebrew cask for", "package an app for homebrew", "submit to homebrew-cask", "make a cask", "contribute a cask", or wants to package a macOS application for Homebrew.

Overview

Publishermalob
Repositorynix-config
Skill namenew-cask
Stars
463
Forks
37
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by malob on GitHub. Read the source before you install it.

Installation

Install the New Cask AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/malob/nix-config/tree/master/configs/claude/plugins/homebrew/skills/new-cask
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/malob/nix-config.git /tmp/nix-config
mkdir -p .claude/skills
cp -r /tmp/nix-config/configs/claude/plugins/homebrew/skills/new-cask .claude/skills/new-cask
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable New Cask in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads New Cask on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so New Cask is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Creating a New Homebrew Cask

You are orchestrating the creation of a new Homebrew cask. This skill coordinates multiple specialist agents and scripts to complete the workflow.

IMPORTANT: This skill runs in the main conversation context. You will use the Task tool to spawn agents for specialized work.

Input

URL provided: $ARGUMENTS

If no URL was provided, ask the user for:

  1. The app name, OR
  2. A download URL (direct link to DMG/ZIP), OR
  3. The product homepage (you'll find the download link)

Workflow Overview

1. Pre-flight checks    → Agent: pre-flight-checker
2. Download & inspect   → Agent: app-inspector
3. Livecheck strategy   → Agent: livecheck-advisor
4. Write cask file      → Agent: cask-writer
5. Testing              → Automated tests, install, createzap, uninstall
6. Submit PR            → Agent: pr-submitter

Create a task list to track progress through these steps.

Step-by-Step Execution

Step 1: Pre-flight Checks

Before investing time, verify the app is suitable:

Use the Task tool:
- subagent_type: homebrew:pre-flight-checker
- prompt: Check if this app is suitable for homebrew-cask submission.
  <include whatever info you have: URL, app name, homepage>

The agent will derive any missing info (app name from URL, homepage via search, etc.) and include it in the output.

Capture from output: App name, homepage, download URL, description - you'll need these for later steps.

Decision point: If the agent returns REJECT, stop and explain why to the user. If CAUTION, inform the user and ask if they want to proceed.

Step 2: Download and Inspect

Download and inspect the app in one step:

Use the Task tool:
- subagent_type: homebrew:app-inspector
- prompt: Download and inspect the app.
  Download URL: <url>
  Homepage: <homepage>

The agent will download the file, compute the SHA256, extract all metadata, and run Homebrew's generate_cask_token tool to get the canonical token.

Capture from output: Suggested token, SHA256, version, bundle ID, app name, min macOS, auto-update info (framework, appcast URL if found), architecture.

Use the suggested token from app-inspector for subsequent steps. This token comes from Homebrew's tooling and handles naming conventions and collision detection.

Note on versioned URLs: If the download URL is unversioned (e.g., App.dmg), the livecheck-advisor may find a versioned URL in an appcast, release feed, or other source. If so, you'll need to re-download using the versioned URL to get the correct SHA256.

Step 3: Livecheck Strategy

Determine how to check for updates:

Use the Task tool:
- subagent_type: homebrew:livecheck-advisor
- prompt: Recommend a livecheck strategy for <app-name>.
  Download URL: <url>
  Homepage: <homepage>
  Update URL: <appcast-or-feed-url-if-found>
  Current version: <version>

Get the recommended livecheck block.

Step 4: Write the Cask

Synthesize everything into a cask file:

Use the Task tool:
- subagent_type: homebrew:cask-writer
- prompt: Write a cask for <app-name> with this metadata:
  Token: <token>
  Version: <version>
  URL: <download-url>
  SHA256: <checksum> (or :no_check if unversioned URL)
  (If separate binaries per architecture, provide URL and SHA256 for each)
  Name: <display-name>
  Description: <one-line-desc>
  Homepage: <homepage>
  Bundle ID: <bundle-id>
  App bundle: <app-name>.app
  Min macOS: <min-version>
  Auto-updates: <yes/no>
  Livecheck: <livecheck-block>
  Architecture: <arm64/intel/universal, only if not universal>

Note: The zap stanza is added later after running createzap during testing.

Step 5: Testing

Automated Tests

Run the validation script:

bash
${CLAUDE_PLUGIN_ROOT}/scripts/test-cask.sh "<token>"

If tests fail, review the output, fix the cask (often brew style --fix handles style issues), and re-run.

For unversioned URLs: Use --skip-livecheck flag.

Install and Validate
  1. Install:

    bash
    HOMEBREW_NO_INSTALL_FROM_API=1 brew install --cask <token>
  2. Launch:

    bash
    open -a "<App Name>"
  3. User verification: Ask the user to sign in or set up the app if needed, then confirm when done.

Zap Discovery
  1. Run createzap (try both app name and bundle ID):

    bash
    brew tap nrlquaker/createzap 2>/dev/null || true
    brew createzap "<App Name>"
    brew createzap "<bundle-id>"
  2. Update the cask - Add the discovered zap paths using the Edit tool. For simple additions you can edit directly; for significant changes, re-invoke the cask-writer agent.

  3. Uninstall:

    bash
    brew uninstall --cask <token>
  4. Re-run automated tests if zap stanza was added.

Step 6: Submit PR

When ready to submit:

Use the Task tool:
- subagent_type: homebrew:pr-submitter
- prompt: Submit a PR for the <token> cask.
  Version: <version>
  Cask path: <path-to-cask-file>
  All tests passed: yes

Error Recovery

If any step fails:

  • The task list shows which steps completed
  • You can resume from the failed step
  • Agent outputs are preserved in conversation history

Reference Documentation

For detailed guidance, agents can read these docs (at /opt/homebrew/docs/):

  • Acceptable-Casks.md - What's allowed
  • Cask-Cookbook.md - Stanza reference
  • Brew-Livecheck.md - Livecheck strategies
  • Adding-Software-to-Homebrew.md - Contribution process

Scripts Location

Scripts are at ${CLAUDE_PLUGIN_ROOT}/scripts/:

  • download-checksum.sh <url> [filename] - Download and SHA256
  • test-cask.sh <token> [--skip-livecheck] - Run audit/style/livecheck

Frequently asked questions

What does the New Cask AI skill do?

This skill should be used when the user asks to "add a cask to homebrew", "create a homebrew cask", "add an app to homebrew", "new cask for", "homebrew cask for", "package an app for homebrew", "submit to homebrew-cask", "make a cask", "contribute a cask", or wants to package a macOS application for Homebrew.

Why use New Cask on TypingMind?

Because you install it once and use it with any model. New Cask is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install New Cask in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/malob/nix-config/tree/master/configs/claude/plugins/homebrew/skills/new-cask. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use New Cask?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with New Cask?

As many as you like. As long as a model supports skills, you can use New Cask with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the New Cask AI skill free?

Yes. It is published on GitHub by malob under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇